Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description bears the full burden and carries it: it discloses that the check is 'Live', that it is paid ('Price: $0.005 USDC'), what gets hard-rejected vs flagged, that `issuer` is ignored for MPT issuance IDs, and that `attest=true` produces an Ed25519-SIGNED attestation. This is rich behavioral disclosure well beyond a generic 'checks token safety' phrasing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose and deliverable are front-loaded in the first sentence, and the denser details (criteria, MPT behavior, attestation) follow in order of importance. It is long, but nearly every clause earns its place; the enumeration of screened criteria could be tightened without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, no annotations, and zero schema coverage, the description covers purpose, verdict vocabulary, cost, both token standards, parameter semantics, and the attestation/verification workflow — remarkably complete. The only gap is the exact response shape beyond 'verdict with reasons'; the tool does not state whether the raw metrics it screens (pool depth, LP-burn fraction) are also returned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain all three parameters, and it does: `currency` is specified as a 3-char or 40-char hex trust-line code OR a 48-char MPTokenIssuanceID, `issuer` is noted as ignored when an issuance ID is passed, and `attest=true` is defined as requesting the signed attestation. Every parameter gains meaning the bare schema lacks.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening phrase 'Live safety verdict for an XRPL token' names the exact verb, resource, and deliverable (a verdict), and the criteria list (clawback, global-freeze, blackhole status, LP-burn fraction, rug blocklist) makes the tool's scope unmistakable. It differentiates from siblings such as check_issuer_reputation, check_transaction, and token_holders, none of which produce a token-level safety verdict.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit routing to alternatives — 'Missing something? Call submit_feedback (free)' and 'verify later with verify_attestation (free)' — and explains the decision between the two token-standards paths (trust-line code vs MPTokenIssuanceID). It stops short of explicitly contrasting with the closest sibling checks (check_issuer_reputation, verify_price), so the when-to-use guidance is strong but not fully exclusionary.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.